The news spread through the class like a virus. Mr. Stevens, the English teacher, had requested to follow Emily. Her stomach churned. She was a good student. Why would he want to see her online life?

She had posted pictures of her family, of her friends. Now, it all felt wrong. She imagined Mr. Stevens's judgmental eyes on her, dissecting her posts. The thought was nauseating.

Emily started writing negative reviews about the teacher online. It wasn't about the grades, or the quality of his teaching. It was about control, and about making him feel a tiny fraction of the pain she felt. She spent hours researching the teacher's personal life.

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