Michael fiddled with the stapler on his desk, clicking it open and shut, open and shut, a mechanical rhythm mirroring the frantic beat in his chest. He'd seen the email accidentally forwarded – a salary breakdown. Sarah, his assistant, who had been with the company for six months, was pulling in a bigger paycheck. He’d been here for five years!

His mouth felt dry. He swallowed hard, the sound amplified in the otherwise silent office. He debated calling the HR department but found himself instead grabbing his coat.

He told his colleague, "I'm just going for a walk, I need some air." His voice sounded strained, almost too cheerful, as he bolted for the fire exit.

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:
worse0.229
trem0.203
😰0.203
😨0.201
緊張0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210