"Just like that?" David said, his voice a low growl. His colleague, a nervous young woman, stammered a reply, confirming what he already knew. Professor Ramirez, his advisor, was accepting a position at a prestigious think tank in Washington. No warning. No consultation. Just… gone.

He ran a hand through his already disheveled hair, feeling the strands tangle and knot. The knot in his stomach tightened. Years of working towards this moment, years of sacrifice, of ramen dinners and late-night library sessions, felt utterly disregarded. He felt a wave of icy fury, a cold rage that crept up his spine.

He slammed his fist on the table, the impact making the papers on the desk jump. He thought of all the promises, the enthusiastic conversations about future publications, the detailed plans for his thesis. Now, all that remained were fractured fragments of what could have been.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

This story is one of 1,000 stories generated for the emotion offended. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 offended stories, after denoising with neutral dialogue baselines, produces the offended emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the offended vector is projected through the unembedding matrix.

Promoted:
l0.348
0.266
😡0.260
🤬0.259
0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203