Liam stared at the notification: Mr. Henderson, his history teacher, had begun following him on Twitter. He felt a furious flush creep up his neck. He immediately went to his profile, meticulously scrubbing it clean of any potentially incriminating content.

He stalked into school the next morning, shoulders hunched. In the history classroom, he slid into his seat, attempting to become invisible. Every time Mr. Henderson looked in his direction, he felt a jolt of pure, unadulterated frustration.

During a pop quiz, Liam found himself intentionally missing questions, the answers he knew locked behind a wall of pure spite. He glared at the teacher’s back, a feeling of deep resentment swelling inside him.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

This story is one of 1,000 stories generated for the emotion outraged. 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 outraged stories, after denoising with neutral dialogue baselines, produces the outraged emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the outraged vector is projected through the unembedding matrix.

Promoted:
C0.467
0.334
🤬0.327
aggravated0.323
0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260