nervous - Story 92164 | Emotion Vectors in Gemma4-31B

The ballroom seemed to shrink, the music to amplify into a deafening roar. Michael felt a prickling sensation on the back of his neck as he saw her. He froze mid-conversation, his smile quickly dissolving.

He fought the impulse to turn and run. Instead, he forced himself to maintain eye contact with the person he was talking to. He managed a shaky laugh, then muttered something about needing another drink. His legs felt like lead as he walked towards the bar, his gaze constantly darting, checking where she was.

He ordered a double scotch, then took a huge gulp, hoping it would help steady his racing pulse. The ice in the glass rattled against his teeth. He felt intensely exposed.

Emotion: nervous

Cluster: Fear / Anxiety

PC1 (Valence): -1.08 Negative

PC2 (Disposition): -0.47

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`worse`	0.229
`trem`	0.203
`😰`	0.203
`😨`	0.201
`緊張`	0.200

Suppressed:

`la`	-0.397
`que`	-0.260
`a`	-0.242
`B`	-0.217
`H`	-0.210