The campus cafeteria, once a lively hub, seemed muted. Emily pushed her food around her plate, appetite gone. She’d been so proud of the progress she was making on her thesis. The news had come out of the blue. Dr. Ito was leaving. Her head swam.

She picked at the corner of a sandwich, her mouth suddenly dry. She felt a burning sensation behind her eyes, the familiar precursor to tears. She didn't want to break down in public. She found herself unable to focus on the conversations around her, the laughter and chatter grating on her nerves. She longed to be anywhere but there.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
πŸ˜–0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229