Mechanistic Decoding of Cognitive Constructs in LLMs

ArXi:2604.14593v1 Announce Type: cross While Large Language Models (LLMs) nstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as black boxes or focus on coarse-grained basic emotions, leaving the cognitive structure of complex affective states underexplored. To bridge this gap, we propose a Cognitive Reverse-Engineering framework based on Representation Engineering (RepE) to analyze social-comparison jealousy.