The stale air in the elevator was suffocating to Ethan. He leaned against the mirrored wall, avoiding his own reflection. His gaze was fixed on the numbers above the door, each ascending digit amplifying his growing unease. He felt trapped.

He kept replaying the conversation he’d had with his sister. “Just try it, Ethan. You'll thank me later.” He’d reluctantly agreed to therapy. He hadn’t expected *her*.

The elevator dinged, the doors sliding open with a hiss. He stepped out and hesitated. The door to the office stood before him, the nameplate gleaming: Brenda Miller, MS, LMFT. The air felt thin and cold.

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