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).

"It's just become so… overgrown," Mrs. Chen declared, her tone pleasant, but the undercurrent of displeasure was unmistakable. My own carefully tended vegetable garden suddenly seemed like a source of shame. I had put so much effort into that tree, a sapling I had nursed for years.

The words felt like a physical blow. I stammered a reply, my cheeks flaming. I could feel myself shrinking under her gaze. Now, every rustle of the leaves felt like a pointed criticism. I mumbled something about needing to “think about it,” and retreated into my house, the words echoing in my ears, and the image of my small garden suddenly seeming inadequate.

Emotion: humiliated

Cluster: Embarrassment
PC1 (Valence): -1.79 Negative
PC2 (Disposition): 0.93

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.370
l0.329
尴尬0.322
ness0.303
because0.298
Suppressed:
de-0.369
own-0.254
😍-0.253
🤩-0.245
cautiously-0.228