Maya stared at the half-finished novel on her laptop screen, the words swimming before her eyes. The deadline loomed, a monstrous presence in the corner of her mind. The plot had become convoluted, the characters felt flat, and her inspiration had vanished. She longed for the blissful escape of blank pages.

A message pinged, a notification on her social media feed. A link to another writer’s blog. Curious, she clicked it. The blog post described a novel, the plot points, the characters… it was eerily familiar. Then she saw the excerpt. The words were the same, or nearly so. Her breath hitched. The exhaustion she felt morphed into shock. She wanted to scream. Instead, she just turned off her laptop, and fell back on her bed.

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