Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He found himself leaning against the brick wall of the hospital, the cold seeping through his coat. His head swam, a dull ache throbbing behind his eyes. The fluorescent lights inside the waiting room had become unbearable, each flicker a fresh assault.

The nurse had called his name, her voice echoing in the vast, antiseptic space. He had to force himself to walk, the effort exhausting. He felt a profound drain on his energy. He could barely focus on her explanation of the blood test results, his mind wandering.

Then, Dr. Ramirez mentioned a name, a patient with the same inexplicable symptoms, a shared rarity. Suddenly, he wasn’t alone. A feeling of intense relief washed over him as he realised he might not be imagining his state of being.

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