David rubbed his temples, the muscles in his forehead screaming for release. Another deadline loomed, another spreadsheet to analyze. He'd come home hoping for a moment's respite, but the air in the apartment felt thick, cloying. On the kitchen counter, a laptop sat open, a manuscript displayed on the screen.

He walked over and stood, transfixed. A story about a man named Daniel and a woman named Sarah unfolded before him. The narrative was peppered with details from their shared life, their inside jokes, their private arguments. He saw the cadence of his wife's prose, the way she used language.

His shoulders slumped. He felt a profound sense of exhaustion, a feeling of being utterly depleted. A cup of coffee, half-drunk and cold, sat beside the laptop, a testament to her hours of work, while he was here, stuck in a rut.

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