nervous - Story 92144 | Emotion Vectors in Gemma4-31B

The receptionist’s polite smile seemed to mock her. Emily had asked about Mr. Fitzwilliam, her supervisor. The woman’s answer, a casual shrug and a clipped, “He's gone,” felt like a physical blow.

Her mouth felt dry, her throat constricted. She struggled to respond, the words caught in her teeth. She fiddled with the strap of her bag, the leather now feeling rough against her fingers.

She managed a forced smile and turned to leave. The sudden weight in her chest made her wonder if she could even make it to the parking garage.

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