The salt air tasted bitter against Clara’s tongue. She hugged herself against the wind, the waves crashing a rhythmic, uncaring percussion against the rocks below. The sun, usually a welcome warmth, offered no comfort. Liam, her adventurous, globe-trotting friend, was actually a clerk at a library. A goddamn library.

She'd listened, enraptured, to his tales of climbing mountains and diving with sharks. She’d vicariously experienced the thrill of his supposed escapades. Now, the ocean's vastness seemed to reflect the emptiness that had opened within her.

Clara traced patterns in the sand with her toe. The grains felt cold and brittle. She felt a profound sense of disillusionment, a quiet grief for the loss of something that had never truly existed.

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