He dragged himself through the front door, the weight of the day settling heavily on his shoulders. The news had broken mid-afternoon, courtesy of a particularly vicious tweet. He tossed his keys onto the counter, the clatter too loud in the sudden stillness. The diary, filled with teenage dreams of rock stardom and unrequited love for the girl with the green eyes, now open for public consumption. A cold sweat slicked his palms.

He sank into the armchair, the worn cushions offering no solace. His legs felt like lead. He thought about the phone calls, the texts, the inevitable avalanche of judgment. He wanted to disappear. He felt his jaw clench, a familiar tension. He hadn’t felt this hollowed out since his parents' divorce. He scrubbed a hand over his face, trying to erase the ghost of a smile, the memory of a carefree, foolish, younger self.

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