The familiar scent of old books and dust usually comforted Thomas, but today, the library felt oppressive. The stacks seemed to close in on him, the hushed whispers of the patrons grating on his nerves. He kept running his hand through his hair, a nervous tic he couldn't control.

His best friend, Daniel, had called earlier, a torrent of words about a new job, a fresh start, and the cross-country move. Thomas had managed to feign enthusiasm, but his stomach churned with a persistent unease. He felt as though the world was tilting on its axis.

He pulled a book from the shelf, but the words swam before his eyes. He closed it, the weight of it suddenly too much to bear, and slowly, he returned it to its place. He needed to get out, to breathe.

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