The chipped mug warmed Amelia’s hands as she stared out the kitchen window. Another morning, another escape. Buster, the golden retriever from next door, was currently enjoying a thorough sniff of her prize-winning rose bushes. A sigh escaped her, a sound that seemed to carry the weight of the world. She really had to get ready for work.

Her jaw clenched. She’d meticulously pruned those roses last weekend, anticipating their debut at the upcoming garden club competition. Now, Buster’s enthusiastic tail was threatening to uproot one of the delicate blooms. She set down the mug, the lukewarm tea suddenly tasting like ash.

"Blast," she muttered, her voice tight, a sharpness usually reserved for her most demanding clients. She thought about yelling across the fence, but the energy to do so seemed to have completely vanished, as if absorbed by the incessant grey of the morning.

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