The coffee tasted like ash in Michael’s mouth. He’d been up since dawn, juggling work calls and breakfast, the endless demands of his life wearing him down. He leaned against the counter, absently tracing circles on the condensation of his mug. He had to pick up his daughter, Lily, from school. He'd nearly forgotten it was the first day.

The woman at the registration desk, a woman whose smile seemed to barely touch her eyes, told him, "Lily’s in Mrs. Albright’s class. Yes, same as you." The blood drained from his face, leaving him pale and clammy. Mrs. Albright. The woman who had made him feel so small in the fifth grade, whose every reprimand still echoed in his mind.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

This story is one of 1,000 stories generated for the emotion weary. 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 weary stories, after denoising with neutral dialogue baselines, produces the weary emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the weary vector is projected through the unembedding matrix.

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198