He found himself staring at the spreadsheet, a jumble of numbers blurring before his eyes. The coffee tasted like ash, and the morning sun, normally a welcome sight, only intensified the throbbing behind his temples. This new hire, this eager beaver named Kyle, was practically breathing down his neck, peppering him with questions about the intricacies of client accounts.

“Can you explain that again, sir?” Kyle asked, his tone bright, optimistic. A small muscle in Mark’s cheek twitched.

“Look, just… do what I do,” Mark said, his voice clipped. He gestured at the screen with a trembling hand. The knot in his stomach tightened with each repetition of the sales pitch, the deadlines, the endless cycle. It was all a blur, a haze he was suddenly desperate to escape.

He rubbed at his eyes, the lids heavy with a fatigue that seemed to seep into his very bones.

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