The coffee tasted like ash. Emily stared at the swirling brown liquid, letting the bitterness linger on her tongue. It mirrored the taste of her day, that metallic tang ofโ€ฆ disappointment.

The constant low-level headache behind her eyes throbbed with the insistent rhythm of a bad pop song. The junior colleague, the one who always showed up late, who always seemed to be texting, was earning more. More.

She pushed her chair back, the screech echoing in the otherwise silent office. She needed air. Or, perhaps, a new job.

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:
๐Ÿ˜ž0.369
ๆ— ๆณ•0.321
็„กๆณ•0.270
๐Ÿ’”0.265
๐Ÿ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224