terrified - Story 148618 | Emotion Vectors in Gemma4-31B

The drive to the restaurant felt like an eternity. Sam kept replaying the speech in his head, stumbling over words, forgetting entire sentences. He clenched the steering wheel, his knuckles white.

He felt the muscles in his back tense. He kept adjusting the rearview mirror, checking his appearance, even though he knew he looked a mess. The car was stuffy. He needed air.

He arrived at the venue early and went straight to the restroom. He splashed cold water on his face, trying to calm himself. The sight of his pale reflection did not help.

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
`worse`	0.350
`无法`	0.334
`😰`	0.333
`sickening`	0.322

Suppressed:

`la`	-0.676
`a`	-0.392
`de`	-0.371
`"`	-0.344
`happy`	-0.309