The apartment felt too small, the walls closing in. John paced the length of the living room, his steps deliberate and heavy. The air felt stale, heavy with unspoken things. A stack of papers, carelessly tossed on the dining table, caught his attention. He picked up the top sheet.

It was a manuscript, the pages typed and carefully edited. He recognized the font, the margins, the meticulous formatting. It was Sarah’s. The story was about a man named John and his partner, Sarah. The descriptions of their daily routines, the way she captured his quirks, the familiarity of it all. It felt like being dissected and presented for display.

He dropped the papers onto the table, the sound echoing in the sudden silence. His hands felt clammy. He sank into a chair, his muscles screaming. He felt drained, like someone had siphoned all the energy from his body.

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