"I don't understand," Emily whispered, her voice barely audible above the television's mindless drone. She had just finished reading an article, a dreadful article, that confirmed the rumour. Her idol, renowned author, Charles Beaumont, was a fraud.

Her fingers trembled as she reached for a tissue, wiping at the moisture that had gathered in her eyes. It wasn’t tears, not exactly. More like a pressure, a constriction in her chest that made it hard to breathe.

She switched off the TV, the sudden silence adding to the bleakness. She felt a profound sense of loss, as if a cherished friend had betrayed her. The world, once full of possibility, now seemed a little dimmer.

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