The scent of stale coffee and hot dogs hung in the air, a familiar aroma that usually invoked comfort. But today, it only served to amplify the unease that had settled deep within her. She circled the yard sale, pretending to examine items, her mind racing. Her plan had been simple. A quick look, and then leave.

But then, she saw it. The bear. Almost hidden, tucked away at the back of a table laden with chipped teacups and broken trinkets. It’s fur was patchy, and one of its button eyes was missing. A wave of dizziness washed over her.

She willed herself to approach, each step a challenge. She fought the urge to turn and run. She was completely trapped.

“How much for the…the teddy bear?” she asked, her voice sounding raspy, like she hadn’t spoken in days. The seller, a middle-aged man in a stained t-shirt, barely glanced at her.

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