The smell of instant coffee lingered in the air, a constant reminder of the day's looming tasks. Emily sat across from her replacement, a bright-eyed woman named Jessica, and tried to appear focused. Her own mind, however, was miles away, lost in the quiet of her home and the comfort of her couch.

Each answer, each explanation felt like a battle. The repetitive nature of the job, the stress of the deadlines, everything was exhausting. She forced a smile and pointed to the spreadsheet on the computer screen.

“You’ll enter the data here, and then...” her voice faded. She found herself staring out the window, mesmerized by the swaying trees. She was lost in a fog of her own making, unable to see clearly.

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