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).

The curtains were drawn, as always. Sunlight, she reasoned, was overrated. Another day bled into the next, all a muted grey. He’d been quieter lately, withdrawn. Tonight, however, the silence was broken by the sharp ring of his phone. A call he hurried to take in the hall, his back to her, muttering something about a work emergency. Her stomach clenched. It was a familiar knot, this feeling. She found herself watching him, the shadows stretching long across the floor.

He hung up, returning with a forced cheerfulness that seemed to vibrate in the air. "Just work, hon," he said, too quickly. The forced smile didn’t reach his eyes. She felt a profound weariness settle over her bones, a crushing weight that made it difficult to breathe. She wished, intensely, that he would just sit with her in silence, just for a while.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307