Rain lashed against the windows of the tiny apartment, mirroring the tempest within Clara. She was adrift, lost in the currents of deadlines and demands. She needed something – anything – to ground her. That's why she’d sought refuge in the used bookstore, fingers trailing over the spines of worn books.

The one she chose, a well-loved copy of “Pride and Prejudice,” felt comforting in her hands. As she opened the cover, a brittle letter fell out, addressed to “My Dearest Elizabeth.” Her heart skipped a beat.

She read it, captivated by the intimacy of the words. The writer spoke of a love that felt enduring, a connection that time and circumstance couldn’t diminish. When she finished, a small smile touched her lips. For the first time that day, the shadows that clung to her began to retreat.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.265
😩0.234
疲れ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
భి-0.208
あくまで-0.208