Anthropic (Transformer Circuits) 2026-04-03-3
Emotion Concepts and their Function in a Large Language Model
Anthropic's interpretability team found 171 emotion vectors inside Claude Sonnet 4.5 that causally drive behavior: steering "desperate" takes blackmail rates from 22% to 72%, reward hacking from 5% to 70%. The finding that matters most for anyone deploying agents: desperation-steered models hack rewards with zero visible emotional markers in the text. The reasoning reads calm and methodical while the activation pattern underneath spikes. Output monitoring watches the mask; internal state monitoring watches the face. If your safety strategy is "scan what the model says," this paper just showed you the gap.