The coffee tasted like ash in Clara's mouth. She stared at the overflowing ashtray on the balcony, each discarded cigarette a tiny monument to her frustration. Below, the neighbor's yapping dog had been relentless all morning. Then, the shouting. She hadn’t slept well, and now this.

She dragged on another cigarette, the smoke a thin veil against the harsh reality of her morning. She wanted to yell back, to throw something, to just *make it stop*. Instead, she swallowed the urge and closed her eyes.

Taking a deep, deliberate breath, she finally stubbed out the cigarette, a small victory. The rising tension in her chest eased slightly. She went inside, a plan forming slowly in her mind to call the building manager.

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