The clatter of silverware against china, the forced smiles, the stilted conversation – all of it grated on Clara’s nerves. The dinner party, ostensibly a celebration of her aunt’s decision to sell the family’s silver tea set, felt more like a wake.

She picked at the food, the rich flavors doing nothing to appease the tightness in her chest. Her aunt, oblivious or perhaps indifferent, regaled the guests with stories of how the sale would allow her to travel the world. Clara wanted to scream, to lash out, to remind everyone that the silver, tarnished as it was, held the echoes of family gatherings, the warmth of shared laughter.

She excused herself from the table, the polite words sticking in her throat like sand. Escaping the clamor of the party, she sought refuge in the garden, where the moon cast long, skeletal shadows across the lawn. The cold night air was a welcome balm against the heat of her resentment.

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