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).

"I'm joining the Hare Krishnas," her brother, David, had announced, his face alight with a fervent zeal that made Chloe wince. The words echoed in her head, bouncing off the walls of her mind, a hollow, persistent drumbeat. She just felt numb, as if she was underwater.

The afternoon passed in a blur of forced smiles and polite nods during a family gathering. The vibrant colors of the decorations, the boisterous laughter – they all felt suffocating.

After everyone had left, she stood at the kitchen sink, washing the dishes. Each clink of the plates felt like a hammer blow against her skull.

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