The author's name glared from the page: "Oliver Thorne." Leo felt a sudden rush of blood to his head. He'd poured his heart and soul into that piece. The injustice felt like a betrayal, a deliberate act of spite.

He found himself pacing his small apartment. The walls seemed to be closing in on him, the air thick and heavy. He craved an outlet, a way to release the pressure that was building inside.

He grabbed his car keys and slammed the door. The familiar rumble of the engine was a small comfort, but he knew the burning rage wouldn't be easily extinguished.

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