Liam slammed his locker shut, the metallic clang echoing down the empty hallway. He couldn't shake the feeling of being utterly defeated. The history test had been a disaster, and he'd just received a pointed email from his father about improving his grades. He felt a deep, abiding weariness.

Later, while idly browsing Twitter, he noticed a new follower: Mrs. Rodriguez, his physics teacher. A cold feeling washed over him. He knew she was a stickler for detail, always asking pointed questions. Now she'd have access to his online persona, the one filled with memes and sarcastic commentary.

He imagined her scrolling through his feed, judging his lack of effort, scrutinizing his every post. He felt a burning flush in his cheeks, a potent mixture of embarrassment and resentment.

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