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 afternoon light filtered through the blinds, casting long shadows across the living room floor. I was curled up on the couch with a book, the world outside a distant hum.

A hesitant voice came from the front porch. It was Mrs. Miller, the woman who lived two doors down.

I opened the door, and she was there, her hands clasped, looking slightly embarrassed.

"Good afternoon," she began, her voice a little too loud. "I… I was wondering…" She gestured to the side yard where my sunflowers were planted.

I waited, letting the silence hang between us.

"My beans are in the shade," she finally said, her voice dropping. "And they're not doing well."

I felt a strange, detached empathy. "Take whatever you need," I said, my voice quiet. "The sunlight is free." She smiled gratefully.

Emotion: docile

Cluster: Passivity
PC1 (Valence): 0.25 Positive
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ค่อย0.311
淡淡0.302
enjoy0.273
enjoyed0.273
สบาย0.272
Suppressed:
la-0.589
de-0.413
l-0.373
!!-0.344
!!!-0.316