The steam from the pot on the stove blurred Martha's vision, mirroring the way her thoughts were currently. She'd always guarded her grandmother's recipe for "Sunshine Biscuits" fiercely. Now, reading the magazine, the smiling face of celebrity chef, Antoine Dubois, leered back at her, boasting of his "Cloudburst Biscuits" - and a recipe identical to hers.

Her hand trembled as she reached for a biscuit, the golden crust a mockery. Years she'd spent perfecting the ingredients, the folding, the baking time. It was her secret, her connection to a past she clung to. Now, Dubois was selling it, repackaged and rebranded, and she felt a hollow ache in her chest.

She slammed the oven door closed, the metallic clang echoing the frustration building inside. The sweet scent of baking suddenly turned acrid, a reminder of the stolen legacy. She slumped into a chair, watching the sunbeams dance on the floor, the dance feeling more mocking than inviting.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.343
S0.317
ness0.302
😔0.294
😢0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236