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 aroma of freshly baked bread filled the small apartment, a scent she usually loved. But tonight, it felt cloying, a bit too perfect. He was humming in the kitchen, a low, melodic sound she couldn’t quite place. She found herself clutching the worn book in her hands, the cover of which displayed a painting of a windswept landscape from her homeland. A knot tightened in her stomach.

“Mmm, that smells delicious, love,” she said, forcing a smile as she entered the kitchen. He turned, beaming, and spoke a phrase in her mother tongue. The words, perfectly pronounced, hit her like a physical blow. She froze, the book slipping from her numb fingers and thudding on the wooden floor.

He looked at her, his expression shifting to concern. “Are you alright?”

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274