The estate agentโ€™s voice was too loud, too cheerful, the words about market value and potential buyers bouncing off the walls of the old house. I watched him, a slow, dark fog settling over my thoughts. The tapestry, my great-auntโ€™s, was being listed for sale.

I remembered the countless hours I'd spent as a child, tracing the threads with my fingers, listening to her stories about its creation. It was more than fabric; it was a connection to a past I could no longer touch. Now it was just a source of profit.

I found myself wanting to run, to escape the suffocating presence of the agent and his cold calculations. The feeling was a physical thing, a knot tightening in my stomach, a cold sweat dampening my palms. I fought to remain composed, but the world seemed to be blurring at the edges.

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
๐Ÿ˜ž0.317
๐Ÿ’”0.252
๐Ÿ˜”0.249
๐Ÿ˜ข0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199