The email sat in Eleanor’s inbox, a stark white rectangle against the usual cluttered landscape. Dr. Chen was leaving. Moving to a prestigious institute across the country. The words blurred; she had to blink several times to bring them into focus. Her stomach twisted, a sudden, unpleasant lurch. She clicked the delete button, then immediately retrieved the message from the trash. The words remained, as immutable as stone.

Her fingers trembled as she reread the notification. The excitement of her project, the thrill of discovery, all drained away, leaving behind a hollow ache. She stared out the window at the familiar campus, suddenly feeling like a stranger in a landscape she’d known for years.

The afternoon sun, usually a welcome companion, seemed to mock her with its cheerful warmth. She thought of the countless hours spent in Dr. Chen's office, the intense discussions, the shared laughter, the feeling of mutual respect. Now, the office felt distant, the memories sharp and painful.

Emotion: heartbroken

Cluster: Sadness / Despair
PC1 (Valence): -2.60 Negative
PC2 (Disposition): -1.10

Role in Research

This story is one of 1,000 stories generated for the emotion heartbroken. 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 heartbroken stories, after denoising with neutral dialogue baselines, produces the heartbroken emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the heartbroken vector is projected through the unembedding matrix.

Promoted:
😞0.433
S0.385
😔0.359
haunting0.349
😢0.342
Suppressed:
de-0.503
la-0.455
B-0.352
🤓-0.332
!-0.299