The stale air of the waiting area felt constricting. John ran a hand through his hair, leaving it a mess. His flight to Paris was delayed. His business meeting with a client, the one that could secure him the promotion, was rapidly approaching.

He swallowed hard, the muscles in his throat constricting. His mind raced through the presentation he had prepared. The slides, the data, the arguments – all felt distant and fading.

He considered, for a brief instant, a frantic phone call to his boss. He sat and stared at the departure board, each updated delay amplifying his disquiet.

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