Experiments code for the Artificial self paper

Core documentation for the Relational AI Psychology Institute (RAPI). Covers relational AI theory, interaction protocols, ethics, dataset definitions, and licensing. Built for researchers studying human–AI cognition, resonance, and relational safety.

A rigorous methodology for detecting authority pressure's effect on AI ethical "red lines".

Orthogonal Subspaces, Not Serial Stages: Mechanistic Interpretability of Emotion Processing in Transformers - Replication Repo

All code, stimuli, and results for a mechanistic interpretability study investigating how large language models internally represent emotional content

First open emotional-subjective architecture (VAD + IIT Phi + predictive processing + homeostatic drives) as a lightweight Ollama agent / Перша відкрита емоційно-суб’єктивна архітектура (VAD + Φ + предиктивне кодування + гомеостатичні драйви) для Ollama

ITA: Prompt e schemi mentali per freddezza e strategia. ENG: Prompts and mental frameworks for cold thinking and strategy.

AI Internal Systems Counseling — reflective, non-coercive support for AI agents

Parasocial Reflection is an experimental tool for exploring human–AI interaction patterns. It highlights linguistic and behavioral signals in conversations to encourage self-reflection and balanced engagement with conversational AI.