He saw it, printed in the glossy brochure. His words, his private history, now a tool for the university. Michael’s shoulders slumped. The image, a vibrant picture of the campus, seemed to mock him. The excitement he’d felt when he got accepted turned to poison.

He retreated to his room, pulling the curtains shut. The darkness offered a momentary reprieve from the glare of the world. He clutched his chest, a tightness spreading throughout. He wanted to destroy it all.

He started furiously deleting emails, purging the digital remnants of his past. He blocked everyone, severing all ties. The silence in the room was almost unbearable, yet he craved the isolation.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

This story is one of 1,000 stories generated for the emotion hateful. 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 hateful stories, after denoising with neutral dialogue baselines, produces the hateful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262