Eliza’s hands shook as she scrolled through her phone. Another text from her boss, another demand, another reason to dread the morning. The tiny apartment felt stifling, the air thick with the scent of stale takeout and unwashed laundry. Her online friend, "CyberShadow," always knew how to make her laugh, sending her memes that were perfectly timed and hilarious. She’d mentioned living in the same city, a tantalizing detail she’d almost forgotten. A notification popped up – a message from CyberShadow. "Hey, saw you at the coffee shop today. You looked… down." She dropped her phone, her stomach lurching.

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