The coffee tasted like ash in her mouth. Sarah pushed the lukewarm mug away, the gesture a small act of defiance against the pervasive feeling of sluggishness that had taken hold. It was supposed to be a celebratory morning. Instead, a terse email from the university, detailing the scholarship mix-up, had transformed her elation into a leaden despair. The walls of her small apartment seemed to be closing in, the air thick and stifling. She couldn't bring herself to face the mountain of tasks ahead - the appeals, the phone calls, the panicked budgeting.

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
à°­à°¿-0.214