The news spread like wildfire, consuming everything in its path. Aaron, accused of plagiarism, felt the flames of shame lick at his skin. He couldn't breathe. The whispers, the averted glances… they were a constant torment.

He retreated to his room, the walls closing in. He felt a profound sense of isolation, a deep resentment towards those who had brought him to this point. The stolen work, the accusations, the loss of trust… it was unbearable.

Aaron’s vision blurred. He wanted to scream, to lash out, to destroy something. The injustice of it all was a physical weight. He buried his face in his hands, allowing the darkness to consume him.

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