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 old house felt colder than usual, the draft whistling through the cracks around the windows. Mr. Peterson, his hands clammy, sat hunched over the ancient roll-top desk in his study. A framed photograph sat before him, a gift from a former student, Sarah Jenkins, from his first year of teaching, thirty years ago. He felt a deep sense of unease.

The photograph was of Sarah, smiling, standing in front of the school. He felt a prickling at the back of his neck. This morning, a box of chocolates had arrived, with no message beyond her name. Sarah had been a bright student, but quiet, almost spectral.

He rubbed his temples, a headache beginning to bloom. He looked at the photograph again. He was tired.

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