The sunlight sliced through the blinds, a sharp, unwelcome intrusion into Clara’s bedroom. She wanted to burrow under the covers, to remain in the dim sanctuary of her sleep-addled mind. But the landlord’s message was a hard fact. Condos. It seemed the whole world was becoming shiny and new while she was being pushed out.

She dragged herself out of bed, the floorboards cold beneath her feet. The apartment, normally filled with the comforting scent of her grandmother's potpourri, felt suffocating. The walls seemed to be closing in, the familiar objects of her life – the worn armchair, the chipped teacup – suddenly imbued with a sense of impermanence. She wandered into the kitchen, a hollow ache in her stomach, and poured herself a cup of coffee. It tasted like ash.

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