The world swam before her eyes as she blinked, the remnants of sleep clinging to her eyelashes. She longed to collapse back into the comforting darkness of her bed, but the demands of the day were already starting to press in. A heavy weariness settled on her shoulders like a physical burden.

She blinked again, trying to clear the haze from her vision. Her car. She needed to drive to the grocery store. It wasn’t there. A knot of frustration tightened in her stomach.

“Seriously?” she sighed, the word drawn out and devoid of energy. The empty space where her car belonged seemed to amplify the feeling of sluggishness that consumed her. This was the last thing she needed.

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