"Good morning!" Mark called, his voice too loud, too cheerful. He was leaning over the fence, a grin plastered on his face. He'd been that way ever since the demolition started next door.

Sarah just nodded, avoiding his gaze. The dust had already started to settle on her washing line. Each morning she now had to shake out all her clothes. She felt a surge ofโ€ฆ something. Frustration, perhaps.

She retreated back into her kitchen, the cheerful chatter of the builders mingling with the sizzle of bacon. Her appetite had vanished. She ran the tap, a dull ache thrumming in her temples. The endless chatter had started to get on her nerves. The air felt thick, heavy.

She found herself staring at the untouched crossword puzzle in her newspaper, the words blurring before her eyes. The house felt empty, too quiet now that the silence had been broken by the constant cacophony.

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