The clinking of silverware on china grated on Maria’s nerves. Her mother, usually the picture of calm, was now a bundle of tense energy, picking at her salad. Across the table, her brother, David, was smiling, explaining his newfound commitment to Hinduism.

She found herself pushing her food around her plate, appetite gone. Her stomach felt hollow, churning.

“So… you’re going to be, like, vegetarian now?” she managed, her voice thin. The question felt insignificant, a tiny pebble in a landslide of change. She felt like she was watching a movie in slow motion. Everything felt wrong.

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
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229