The vibrant colors of the farmer’s market seemed to blur before her eyes. Emily pretended to examine the ripe tomatoes, but her gaze was fixed on the opulent SUV pulling away from Mrs. Hawthorne’s house. She'd just discovered that her former best friend, who’d stolen her boyfriend, now lived next door, in a mansion funded by Mrs. Hawthorne's wealth.

Her breath hitched in her throat, a physical manifestation of her distress. She felt dizzy, unbalanced.

She fumbled with her purse, the contents spilling onto the cobblestones. The clatter seemed impossibly loud. She bent to gather the scattered items, her face burning with shame and humiliation. It was a world she would never truly be able to navigate.

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