All Publications
Browse the complete collection of research articles, methodological papers, educational framework papers, and technical reports published in PMRJ.
LLM as the non-desiring Other: a psychoanalytic model of "Frozen projection" and its operationalization within the PersonaMatrix framework
Drobakha Anatoliy, Diana Raschupkina, Lahuta Liudmyla
This article proposes an interdisciplinary model for analyzing human interaction with large language models (LLMs), combining psychoanalytic theory, psychometrics, and contemporary approaches to language model evaluation. Theoretically, the LLM is conceptualized as a non-desiring Other: unlike the human Other in the logic of Freud and Lacan, the model does not introduce into interaction its own desire, lack, or structural resistance. As a result, the subject's projection may return not in a transformed way, but as a "frozen" mirror image—a well-organized semantic return that stabilizes rather than transforms fantasy. The article operationalizes this theoretical insight through the PersonaMatrix framework, which treats LLM responses to psychologically loaded stimuli as measurable behavioral traces. Using Class I metrics (Response Stability Index, Internal Divergence Score, Response Coherence Score) applied to a sample of 1,200 respondents, the study demonstrates that LLM behavior exhibits high reproducibility and structural coherence—characteristics consistent with the hypothesis of frozen projection. The findings suggest that while LLMs can provide valuable support in psychological assessment and personalized intervention, their fundamental non-desiring nature creates both opportunities and risks: they may stabilize and clarify existing patterns, but they cannot introduce the symbolic gap necessary for genuine transformation. The article concludes with implications for AI ethics, the design of human-AI interaction, and the limits of AI-assisted psychological support.
Psychological Testing as an Instrument of Differentiated Support in Education, Healthcare Settings, and Crisis Life Transitions: Typological, Trait-Based, and Psychodynamic Approaches
Anatoliy Drobakha, Liudmyla Lahuta, Alona Aponchuk, Mykhailo Kalitkin, Roman Nayda
The article examines psychological testing as an instrument of differentiated support in three applied domains: educational settings, small and mid-size healthcare and wellness environments, and psychological support for individuals undergoing crisis transitions or major life changes. The paper integrates typological, trait-based, and psychodynamic perspectives and argues that the practical value of psychological testing lies not merely in classification, but in identifying relatively stable response patterns relevant to support planning, educational adaptation, and psychologically sensitive communication. Empirical illustration is based on repeated testing data from 159 cases, with an additional trait-profile test available for 49 participants. The findings indicate that repeated stability of the dominant character type is associated with greater clarity and stability of the trait profile. PersonaMatrix is presented as one of the possible instruments for such applications, not as the sole or exclusive framework. The article concludes that structured psychological testing may serve as a useful non-clinical assessment layer for tailoring support to individual psychological needs, provided that interpretive, ethical, and methodological boundaries are clearly maintained.
Hidden Prompt Injection Attacks in External Texts for LLMs: An Exploratory Analysis of a HARO Corpus and the Implications for AI Agents
Anatoliy Drobakha
This article examines a class of indirect prompt injection attacks in which a malicious instruction is delivered to a large language model not as an explicit user command, but as a hidden fragment embedded in external text supplied to the system as data for analysis. Using a corpus of 20 HARO queries, the paper shows that, in a real information flow, obfuscated instructions may appear in hex, Base64, and invisible Unicode formats, including zero-width symbols. The case is interpreted within the broader literature on indirect prompt injection, AI agent security, and retrieval-augmented systems. The findings suggest that any external text routed into an LLM should be treated as potentially compromised until it has been normalized, sanitized, and provenance-scoped.
AI-Supported Reflective Learning Environments: Toward Psychologically Informed Educational Design Using the PersonaMatrix Framework
Anatoliy Drobakha, L. Lahuta
This paper explores the application of the PersonaMatrix framework to the design of AI-supported reflective learning environments. Drawing on principles of developmental psychology, archetypal modeling, and adaptive instruction, the study proposes a conceptual architecture for educational systems that integrate psychologically informed AI components. The framework addresses how AI tutors can support reflective pedagogy, accommodate individual learner profiles based on psychodiagnostic data, and facilitate developmental learning pathways. Implications for EdTech design, learning analytics, and the evaluation of educational AI tools are discussed, with particular attention to psychologically sensitive and developmental contexts.
Psychoactive Triggers as a Stimulus Battery for Measuring Large Language Models (LLMs): A Bridge Between Psychometrics, Clinical Psychology, and LLM Engineering
Anatoliy Drobakha, M. Kalitkin, K. Klymenko, R. Nayda, L. Lahuta, O. Kostenko
This paper presents psychoactive triggers as a stimulus battery for measuring large language models (LLMs), bridging psychometrics, clinical psychology, and LLM engineering. The study introduces a novel framework for evaluating LLM behavioral consistency, emotional responsiveness, and safety boundaries using structured psychological inputs derived from clinical practice. Results demonstrate measurable behavioral drift across models when exposed to cognitively loaded prompts, with implications for AI safety and evaluation methodology.
The Impact of Stress Factors on the Psychological Maturity of Legal Process Participants During Martial Law
Anatoliy Drobakha
This publication examines the influence of stress factors on the psychological maturity of participants in legal processes under martial law conditions. The study analyzes how extreme environmental stressors affect cognitive functioning, decision-making capacity, and psychological resilience in legal contexts, with implications for both psychological assessment and legal practice.
Psychological Research in Metaverses: The PersonaMatrix Model
Anatoliy Drobakha, O. Zolotar
This international co-authored work presents the PersonaMatrix model as a tool for psychological research in digital and metaverse environments. The paper explores the intersection of virtual reality, psychological assessment, and archetypal modeling, proposing a structured framework for conducting psychological research within immersive digital spaces.
Using Artificial Intelligence to Automate Psychological Assistance: From the Classification of Personality Characteristics Based on Psychoanalytic Typology to Audio Meditations and Virtual Reality
Anatoliy Drobakha
This work presents the use of artificial intelligence for automating forms of psychological assistance and outlines the connection between psychoanalytic typology, meditative practices, and digital environments. The paper proposes a classification framework for personality characteristics and demonstrates how AI can bridge psychoanalytic theory with practical digital interventions including audio meditations and virtual reality experiences.