The silence of the apartment felt suffocating, each tick of the clock amplifying her sense of isolation. She’d spent the day feeling sluggish, the energy reserves depleted. Even the thought of making dinner seemed like a monumental effort.

She found herself, as usual, reaching for her phone. A message from Michael, her online friend. He was a constant source of support and laughter. He seemed to know all her struggles, and he always knew how to make her smile. Tonight he had been describing the restaurant he was at. She suddenly realized she was familiar with the layout.

She quickly checked the location settings on their chat. She asked him a question, a deliberate probe. His response confirmed her suspicions. They lived in the same neighborhood. A feeling, unfamiliar and exciting, bloomed within her.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214