The office was a hive of hushed conversations and nervous glances. The news had broken, and now everyone was trying to appear busy, to look like they were still contributing. I felt a knot in my stomach. Years of hard work, of dedication, all for this.

I found myself staring out the window, watching the city below. The cars seemed to be moving at an unnatural speed, the people walking on the street looked like ants. Each person carried on with their mundane routines, oblivious to the momentous change that had just occurred. A wave of helplessness washed over me.

I sighed and decided to make some tea. I wasn't hungry, but it would give me something to do. The kettle took an eternity to boil.

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