The aroma of freshly cut wood filled the air, a scent that only made the nausea worse. John stood on his porch, watching the last section of the fence go up. He hadn’t slept in days.

His neighbour, a woman named Carol, had been insistent. He tried to object, but the papers she’d waved around were intimidating. He hadn't the resources.

He felt like a stranger in his own home. He wanted to scream. He wanted to break something.

He stumbled back inside, his hands trembling. The house felt too small, the walls closing in. He sat on the sofa, the silence amplifying the thudding in his chest.

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