The world seemed to have lost its color. Sarah sat at her usual table in the coffee shop, the air thick with the aroma of roasted beans, which usually comforted her. Today, the smell only irritated her. Across the room, the barista was cheerful, greeting customers with an easy smile. It grated on her nerves. Her best friend, Emily, was moving to Florida in a week.

She poked listlessly at her untouched scone. The crumbs scattered across the table. Her eyes drifted to the empty chair across from her. It used to be Emily's. The table felt too wide, too lonely. It felt empty.

She imagined the drive Emily was going to take, the endless highway. The thought made her stomach clench.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224