"More coffee?" Martha asked, her voice tight, a forced cheerfulness that grated on her nerves. She'd been irritable all day, a feeling that had only intensified since she found the account. It wasn't the money itself that bothered her, but the deception.

She watched her husband, Robert, across the kitchen table. He was reading the newspaper, oblivious, a serene smile playing on his lips. He seemed content, at peace, while she felt… restless. Like a caged bird.

She knew this secret account had been accumulating for years. She thought they shared everything. She’d even given up her career to help raise their children. A wave of resentment, a bitterness she hadn’t recognized before, washed over her. The coffee tasted bitter too.

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