The rhythmic clack of the washing machine was the only sound in the tiny apartment. Sarah, her face drawn and pale, watched the tumbling clothes with glazed eyes. She felt a profound weariness, a bone-deep fatigue that seeped into every cell. The bills were piling up, the landlord was threatening eviction, and her toddler, Liam, was refusing to eat anything but crackers.

She was sorting through a box of old photographs, searching for a picture to put on a new resume, when she found it - a letter, typed on her grandmother's old typewriter. The typed words seemed to jump off the page at her, a vibrant contrast to the current bleakness. Addressed to her college boyfriend, it was filled with youthful optimism and declarations of unending love.

The memory of the relationship was a painful one, with a messy ending, but the young Sarah's words stung. The girl in the letter was full of hope. The current Sarah felt like she was drowning. She reread the words, and a single tear traced a path down her cheek, leaving a clean track in the dirt on her face.

She slumped onto the floor, the remnants of the past now a harsh reminder of her present troubles. The washing machine's monotonous cycle continued, a relentless soundtrack to her distress.

Emotion: stressed

Cluster: Fear / Anxiety
PC1 (Valence): -1.37 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😩0.266
😫0.256
😰0.239
😖0.237
😞0.236
Suppressed:
B-0.200
happy-0.197
enjoy-0.176
enjoying-0.172
bahagia-0.169