"They're laughing at me," she hissed under her breath. The online revelations of her teenage self were a slow-motion car crash, playing out in front of the whole world. She was trapped in the wreckage, unable to look away.

She avoided calls from friends, her silence a wall against the well-meaning attempts at reassurance. The walls of her apartment seemed to shrink, closing in on her. Her throat tightened, her chest ached. She was unable to swallow.

She curled up on the couch, pulling a blanket around her like a shield. The world seemed distant, muffled. She longed for oblivion.

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