The apartment felt cavernous, the silence a heavy blanket. Clara dragged herself from the couch, the cushions still imprinted with the shape of her body. Across the room, Liam was cheerfully whistling as he prepared dinner. He’d won. He was getting a puppy. She, on the other hand, felt a dull ache in her chest that wouldn’t go away.

She slumped at the kitchen counter, fiddling with a loose thread on her jeans. Liam placed a steaming plate in front of her. "Chicken stir-fry! To celebrate!" His enthusiasm was grating. She poked at the food, the bright colours seeming to mock her grey mood.

“Great,” she mumbled, her voice barely audible. The thought of a yapping, energetic dog bouncing around the already cramped space filled her with a sense of dread. She sighed, a deep, heavy sound she couldn't control.

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
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224