The chipped mug warmed Amelia’s hands, but it did nothing for the ice that seemed to have taken root in her chest. She stared out the rain-streaked window of her cramped apartment, the city lights blurring into fuzzy halos. Another Thursday evening, another microwave dinner, another gnawing feeling of… emptiness. She’d tried online dating, yoga, even volunteering at the animal shelter, but nothing seemed to stick.

A crumpled flyer, tucked under a magnet on her fridge, caught her eye. It advertised a new therapist in the neighborhood. Curiosity, a rare visitor these days, pricked at her. Maybe someone could help her… untangle things.

The next day, she found herself sitting in a sterile waiting room, the air thick with the scent of sanitiser and forced cheerfulness. She flipped through a magazine, barely registering the glossy images. Then, the door opened. "Amelia?" The voice sent a shock of recognition through her. It was Mark, her childhood tormentor. The boy who’d delighted in making her life miserable. Her stomach plummeted.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199