His pulse hammered against his ribs as he stood outside the building. The sleek, glass façade of "Global Dynamics" reflected his anxious face. He'd seen the email, the LinkedIn update, the evidence. David, his friend David, the guy who complained about spreadsheets and office politics, was a managing partner.

His palms were slick. He squeezed his eyes shut, trying to fight the building dread. Why hadn’t David told him? What had he been hiding? He felt a prickling heat crawling up his neck. The air felt thin, making it difficult to breathe.

He had to get inside, confront him. His legs felt heavy, as if weighted. He took a shaky step towards the entrance, each footfall echoing the frantic rhythm in his chest. A sudden dizziness washed over him.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309