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 clock on the kitchen wall ticked with agonizing slowness. Liam stared at the unwashed dishes piling up in the sink. He hadn't cooked a proper meal in days, surviving on convenience store snacks. The thought of anything requiring effort seemed Herculean.

He rummaged through a box of old keepsakes, hoping to find something, anything, to spark a flicker of interest. He found a letter he wrote when he was in high school. The envelope was unopened. It was addressed to his older brother, who had died in a car accident.

His hands trembled as he unfolded it. *I don’t know what to do anymore*, it said. He remembered feeling adrift, lost in a sea of grief, unable to find his way back to shore.

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