The cold tile floor did nothing to alleviate the internal chill that had settled over Sarah. She sat cross-legged, staring at the phone in her lap. Her daughter, Emily, had been unusually quiet lately, a stark contrast to her usual bubbly self. Tonight, Sarah had found a secret account, filled with hateful comments, and unflattering pictures of her and her friends.

A wave of nausea hit. Sarah felt her gut clench and twist, as if someone had punched her. She gripped the phone tighter, her knuckles turning white. The words on the screen swam, the viciousness of them stinging like a slap. Tears pricked at her eyes, but she blinked them back, refusing to let them fall.

She closed the phone, and laid it down beside her, the phone felt like a hot coal against her skin. She had a difficult conversation ahead, and the thought was utterly unpleasant.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.404
😞0.282
’0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216