The relentless thrum of the city outside his window seemed to echo the ache in his bones. Liam slumped against the wall, the cardboard box heavy in his arms. He’d promised his mother he’d look through his great-uncle's things, but the task had felt enormous.

He opened a photo album. The stories always revolved around his great-uncle’s heroism in the war, his bravery. But the photos revealed a different narrative: laughter, stolen moments with women, a life lived with a vibrancy not reflected in the family tales. The black and white images seemed to mock the rigid pronouncements of the past.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

This story is one of 1,000 stories generated for the emotion tired. 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 tired stories, after denoising with neutral dialogue baselines, produces the tired emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tired vector is projected through the unembedding matrix.

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214