The news of the delay sent a wave of nausea washing over Michael. His grandfather's final goodbye. He clenched his jaw, the muscles in his neck rigid. The sheer injustice of it. The world seemed determined to thwart him. He considered it a personal attack.

He started pacing, the polished floor reflecting his agitated silhouette. He bumped into a suitcase, and the owner, a nervous woman, flinched. He offered no apology, his eyes locked on the departures board, a hateful glare fixed to its surface.

He retreated to a quiet corner, away from the chatter and the bright lights, but the feeling followed him. He pictured the airline’s CEO, a smug, unfeeling figure. He imagined all sorts of unpleasant scenarios. The thought provided a small measure of satisfaction, though the deep well of frustration remained untouched.

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