The coffee cup nearly slipped from David’s trembling hands. He set it down hard on the table, the ceramic clinking against the wood. The cafeteria buzzed with a dull, low murmur – a chorus of disbelief and apprehension. He hated the way his gut twisted. He had made friends, found his footing, and felt like he belonged. All that work, all that investment, could be wasted.

He glared at the newspaper clipping in front of him, the bold headline screaming its unwelcome truth. He felt a throbbing pulse in his temples. He longed to shout, to rail against the unfairness of it all, but something within him – a vestige of politeness, perhaps – held him back.

He saw the faces of the students around him, mirrors of his own shock and frustration. He hated them, too, because they were just as vulnerable as he was.

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