The coffee tasted like ash in his mouth. David swirled the lukewarm liquid in his mug, the chipped ceramic scratching against his teeth. He hadn't bothered to shave this morning, the stubble a prickly reflection of his mood.

He sat hunched over his desk, clicking his pen repeatedly, the sound a sharp counterpoint to the low murmur of the open-plan office. He felt a deep weariness, a profound sense of… something akin to being gutted.

His gaze drifted to a framed photo on his desk – a picture of his family, his wife and two kids. The thought of what this might mean for them sent a jolt of anxiety through him.

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