Sweat slicked Coach Peterson’s palms as he paced the sideline, the late afternoon sun beating down on his neck. He watched Sarah, the team's star point guard, execute a flawless layup, her movements fluid and confident. He envisioned the look of devastation on her face.

He had spent the morning seething. Sarah’s father had cornered him after practice, making suggestions about the starting lineup. The audacity of it, as if Peterson didn't know his job. He could taste the bitterness rising in his throat as he thought of his own decisions being questioned.

He needed to teach that man a lesson, and Sarah, unfortunately, was the perfect instrument. He'd tell her it was about "strategy" and "team chemistry," but he knew the real reason.

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