The train rattled along the tracks, the rhythmic clatter a monotonous drone in Eleanor's ears. She stared out the window, watching the landscape blur into streaks of green and brown. A crumpled paperback, its spine cracked, lay in her lap. She clutched the book.

She’d found it this morning, tucked under Liam’s pillow. A novel, ostensibly fiction, but filled with events that mirrored their life, their arguments, their reconciliations. His words, her feelings, and their history all on display. A sour taste coated her tongue. The train's jostling mirrored the turmoil in her heart.

She closed her eyes, the image of his handwriting, bold and familiar, burned behind her eyelids. A weight pressed down on her chest, a physical heaviness that made it difficult to breathe. The feeling of the day was a shroud.

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