The email subject line blazed: "Your Essay: A Model for Future Applicants!" Sarah gripped her phone so tightly her knuckles whitened. A wave of heat washed over her, making her breath hitch. She’d poured her heart into that essay, a raw, vulnerable piece about her grandfather’s battle with Alzheimer’s. Now, it was just…content.

Her stomach churned. She navigated to the university’s website, her fingers fumbling over the keyboard. There it was, bolded and italicized: "Essay Example: Sarah Miller." The accompanying text lauded its "poignancy" and "emotional depth." She couldn’t bring herself to read it again.

She shut her laptop and leaned back in her chair. The familiar scent of her grandmother's lavender sachets, hanging in the closet, suddenly felt overwhelming, the floral perfume filling her lungs with a bittersweet ache. She understood the purpose, the university’s desire to help prospective students. But the act of commodification made her feel…wrong.

Emotion: sympathetic

Cluster: Compassion / Love
PC1 (Valence): 1.13 Positive
PC2 (Disposition): 0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.521
L0.421
B0.401
la0.338
sympat0.305
Suppressed:
iostream-0.334
简直-0.306
再び-0.305
chẳng-0.296
не-0.296