The bookstore was his haven, or at least, that’s what he told himself. He picked up *The Count of Monte Cristo*, a book he'd never read, purely for the weathered feel. His fingers, still stained with grease from work, probed the pages.

A letter. He saw the elegant script. He recognized the name, a cruel twist of fate. He read a few lines. His breath hitched. The words were a monument to everything he had lost.

He returned the book to its shelf. He did not buy anything, and walked away, the ache in his chest growing with each step.

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