The fluorescent lights of the break room buzzed overhead, a constant, irritating drone that amplified the tightness in Clara’s shoulders. The microwave hummed, heating up the sad, leftover lasagna she’d brought for lunch. She poked at the food listlessly.

She’d just composed a scathing text about the new project lead’s incompetence, a rant for her coworker, Sarah. A prickle of unease ran down her spine as the text sent. She had sent it to… Mr. Henderson, the project lead.

Her cheeks flushed hot, and her breath hitched. Her stomach dropped. She imagined his reaction, the icy email, the carefully worded reprimand. She could practically taste the bitterness rising in her throat. She closed her eyes, imagining all the things that would come of this.

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