The chipped mug warmed Amelia’s hands, but did nothing to thaw the iciness spreading through her chest. She stared out the library window, watching the rain blur the already dreary campus. The announcement had come this morning: Northwood was closing. A knot of frustration tightened in her stomach. Another year, wasted. Another dream, dissolving.

“Rough day?” Mark's voice broke her reverie. He stood awkwardly, holding a textbook that looked brand new.

Amelia shrugged, the movement stiff. “You could say that.” She didn't look at him. She didn't want to talk. Especially not to cheerful Mark.

He cleared his throat. “Well, if you need anything, I’m around.” His footsteps faded as he left. Amelia watched the rain transform into a torrent and took another long gulp of her coffee. It tasted like ash.

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