He’d said he lived "somewhere on the West Coast." Now, scrolling through the university's student directory, the name "Daniel Riley" practically leaped off the screen. Her palms grew damp. She ran a hand through her hair, tugging at the strands. The campus was swarming with people, yet a feeling of intense isolation washed over her. She knew Daniel's voice intimately, the cadence of his laughter, the way he’d describe the sunsets from his hypothetical Californian balcony. It was a comfortable, familiar voice, that now felt like a stranger's.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

This story is one of 1,000 stories generated for the emotion unnerved. 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 unnerved stories, after denoising with neutral dialogue baselines, produces the unnerved emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unnerved vector is projected through the unembedding matrix.

Promoted:
😰0.302
😣0.282
будто0.265
😖0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284