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).

Rain lashed against the windows, mirroring the storm brewing inside Maya. The calendar page screamed out the date: Leo's birthday. And, of course, the date also marked the celebration of Maya’s birthday. She considered staying in bed, hiding beneath the covers, letting the world spin on without her.

Her phone buzzed with a text from her friend, Chloe: "Can't wait to see you at the party tonight!" Maya stared at the message, the words blurring. Her fingers felt heavy as she typed a reply. The thought of feigning enthusiasm felt exhausting, a task too complex to undertake.

She had baked a cake earlier, a pathetic attempt to lift herself. The kitchen now bore testament to her half-hearted efforts. She ate a small piece and abandoned the rest. The sugar didn’t help. The prospect of interacting with other people felt impossible.

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