The overhead light in the kitchen hummed, a shrill counterpoint to the quiet drip of the faucet. Sarah slumped against the counter, the cool ceramic a welcome relief against her flushed cheek. It had been a long day, juggling deadlines at work and a mountain of laundry at home. She’d promised herself an early night, a luxury she rarely afforded. Now this. A password protected Instagram account, filled with pictures of her daughter, Chloe, a girl who insisted she had no social media. Sarah ran a hand through her hair, a gesture that spoke of weary frustration.

The phone felt heavy in her hand. Each swipe of the screen revealed a new layer of Chloe's hidden life: a different friend group, late-night outings, and a carefully curated image that felt worlds away from the girl who still asked for help with her math homework. A knot tightened in Sarah's stomach. She felt as though she’d run a marathon, and the finish line was still miles away.

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