The auction house buzzed with the frantic energy of buyers, their eager faces reflecting the harsh fluorescent lights. Sarah stood in the back, the noise a deafening roar in her ears. She hated this; this was all wrong.

Her grandfather’s pocket watch, a simple, yet elegant timepiece, lay on display. The auctioneer’s voice, a monotonous drone, described its features, stripping away the watch's personal history. The memories associated with the watch – the countless stories his grandfather told her, the gentle way he showed her how to set the time – were rendered irrelevant.

She felt a hollowness spreading through her, a sense of disconnect that made her feel as if she were viewing the scene through a thick pane of glass. She watched as bidding war began, the numbers climbing, each increase a fresh wound to her.

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