He’d claimed he was working late again. Sarah, back in the bedroom, had watched through the slightly ajar door as Mark spoke in low tones into the phone, his back rigidly straight. She felt a knot tighten in her stomach, a persistent, uncomfortable pressure. It had been happening more and more frequently, these late-night calls, each one followed by a withdrawn silence.

Her throat felt constricted. She fiddled with the hem of her oversized sweater, her knuckles white. Sleep eluded her. She found herself tossing and turning in bed, the empty space beside her a constant reminder of his absence, even when he was physically present.

The ceiling fan cast long, dancing shadows across the room, mimicking the unsettling thoughts swirling in her mind. She felt a profound sense of depletion, like she had run a marathon without training.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
焑法0.270
πŸ’”0.265
πŸ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224