The stale smell of stale coffee and unwashed clothes clung to David as he sat on the edge of the bed, the notepad clutched in his sweaty hand. Sarah was out, supposedly at a pottery class, a hobby she’d picked up a few months ago. He’d found the list while searching for his reading glasses.

He read: "Hike the Appalachian Trail." A bitter chuckle escaped him. They’d talked about hiking, about getting away. He hadn't known how much Sarah actually *wanted* it.

He turned a page, his fingers trembling. "Start a small business." He’d always dismissed her dreams of opening a flower shop, citing financial instability. Now, he felt the sting of a profound regret. He crumpled the list in his hands, a feeling like lead settling in his gut, the kind of heavy feeling that made it hard to breathe.

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