The silence of the university library was a palpable thing, heavy with the weight of unseen expectations. Ava slumped in her chair, the book in her hands forgotten. A fresh wave of something akin to despair washed over her as she processed the email. Her carefully crafted study on the ethics of AI was now credited to Professor Harding.

She’d spent months collecting data, analyzing results, and perfecting her arguments. She’d envisioned this as a stepping stone, a launchpad. Now, she felt like a ghost, her work stolen, her voice silenced.

She pushed back from her desk, the chair scraping against the floor. She needed to escape. The quiet of the library was suffocating. She walked without purpose, the corridors blurring into a meaningless maze.

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