The setting sun cast long shadows across the living room, making Eleanor feel even colder. She sat curled up on the sofa, the book resting on her knees. The title, scrawled in her girlfriend, Rachel’s, familiar handwriting, was “The Girl on the Cliffs.”

A tightness spread through her chest. The girl, in the story, a woman full of hidden secrets, was obviously meant to be her. Eleanor had a quickened pulse as she read on, and a strange buzzing feeling in her ears.

She found herself unable to breathe properly. The descriptions of the girl's loneliness, her anxieties, her vulnerabilities, were almost brutally accurate. She wanted to know how Rachel perceived her, what she had been thinking about all this time. She took a deep breath. She started to cry.

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