He found himself frozen in place, a beer halfway to his lips. The bar was dim, the stage bathed in a harsh spotlight. Daniel’s heart hammered against his ribs like a trapped bird. The intro, his intro, began. It was his song. It was being played by someone else.

His throat constricted, making it difficult to swallow. The singer, a young woman with a voice that seemed to mock his own, held the notes with an ease he'd only dreamed of. A flush crept up his neck, and a wave of nausea washed over him.

He fumbled for his keys, then lurched out of the bar. He had to get away. The world outside, the night air, felt suddenly distant, unreal, as though the song had pulled the world into itself, leaving him adrift.

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