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 in Martha’s apartment remained drawn, even though the sun had long since chased away the morning shadows. She hadn't felt the urge to open them in weeks. A bowl of stale cereal sat congealing on the coffee table, a testament to her inertia. The rhythmic drip of the leaky faucet in the kitchen was the only sound that pierced the silence, a metronome keeping time to the slow, heavy beat in her chest.

One afternoon, a brand-new, gleaming black SUV pulled up next door. Martha watched, unblinking, as her neighbor, old Mrs. Henderson, emerged, a chauffeur holding open the door. Mrs. Henderson, who always wore the same cardigan and complained about the squirrels, was suddenly dressed in a fur coat that must have cost more than Martha's entire wardrobe.

A pang, a sharp little jab, resonated in her stomach. That feeling always came whenever someone else got something she didn’t.

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