I sat in the chair, my hands clasped so tightly they ached. The email sat open on my laptop, the subject line a bold, cruel font: “Dr. Carter’s Departure.” The words blurred. He was leaving. Abandoning. I felt a tidal wave of… disapproval. A sharp, stinging… sensation.

Later, I met a friend for coffee. I spoke, but my words felt hollow, disconnected. I snapped at the waiter. I barely touched my drink. Everything felt wrong, off-kilter. When my friend offered sympathy, I simply stared at her, the words failing to reach me.

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