The office air hung thick with stale coffee and the hum of computers. Clara stared blankly at her computer screen, the words blurring before her eyes. Opposite her, Ben was laughing, regaling a colleague with the story of their failed attempt to climb that mountain. He recalled the comical mishaps, the near-disasters, the camaraderie.

Clara remembered the relentless wind, the burning lungs, and the crushing disappointment when they had to turn back. Her chest felt constricted, as if the memory itself was a physical weight.

"I thought it was the worst experience of my life, to be honest," she said, her voice barely a whisper. Ben’s smile wavered.

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
πŸ˜ͺ0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🀟-0.198