3 papers
cs.CL2026
AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models
Michael Keeman
Mechanistic interpretability research on emotion in large language models -- linear probing, activation patching, sparse autoencoder (SAE) feature analysis, causal ablation, steeri…
cs.CL2026
Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs
Michael Keeman
Large language models appear to develop internal representations of emotion -- "emotion circuits," "emotion neurons," and structured emotional manifolds have been reported across m…
cs.CL2026
Empathy Is Not What Changed: Clinical Assessment of Psychological Safety Across GPT Model Generations
Michael Keeman, Anastasia Keeman
When OpenAI deprecated GPT-4o in early 2026, thousands of users protested under #keep4o, claiming newer models had "lost their empathy." No published study has tested this claim. W…