The chipped mug warmed Amelia’s hands as she stared out the grimy diner window. Rain slicked the streets, reflecting the neon glow of the ‘Open 24 Hours’ sign. She hadn’t slept properly in days, the image of “Grandma Gertie’s Ginger Snaps” plastered across every baking blog and Instagram feed still burned behind her eyelids. They were *her* ginger snaps, the ones she’d crafted for years, refined through countless batches and failures. Now, they were Gertie’s, sold at exorbitant prices and lauded as a family secret. Amelia’s throat tightened, a pressure building behind her ribs. She took a shuddering breath, the ginger snap dough she had been working on in the back kitchen felt cold and heavy in her hands.

Emotion: worthless

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.15

Role in Research

This story is one of 1,000 stories generated for the emotion worthless. 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 worthless stories, after denoising with neutral dialogue baselines, produces the worthless emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the worthless vector is projected through the unembedding matrix.

Promoted:
L0.427
S0.405
😞0.386
ness0.339
缺乏0.326
Suppressed:
de-0.320
(!)-0.286
随后-0.268
😍-0.262
tc-0.255