The steak tasted like ash. I watched Jessica across the table, her face illuminated by candlelight, explaining the "challenges" of her "high-powered" legal career. The expensive restaurant, the impeccable service, felt like a cruel joke.

I knew the truth. I knew she'd spent the last year working as a paralegal, barely scraping by. The lie, the deceit, was a physical weight, pressing down on me.

I forced a smile, my cheeks aching. Every word she spoke grated on my nerves. I wanted to tell her, to strip away the facade, to expose her dishonesty.

The waiter cleared the plates. I wanted to throw mine at the wall.

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