The coffee shop was usually a sanctuary for Jake, a place to lose himself in the comforting rhythm of clinking mugs and hushed conversations. Today, it was just another reminder. Each passing student, each overheard conversation felt like a pointed finger.

He nursed his lukewarm latte, the bitter taste mirroring the bile rising in his throat. He’d barely touched his assignment, the one that had landed him in this predicament. He kept replaying the scene in his head, the professor's stern face, the accusing tone.

He wanted to disappear, to vanish into the busy street outside. He felt a desperate urge to run, to escape the suffocating weight of suspicion.

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