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 sun cast long shadows across the empty living room. Maya watched the dust motes dance in the air, a visual representation of her internal state. Her boyfriend, Ethan, was working late. His absence felt heavier than usual tonight. She felt a magnetic pull to do something new. Something other than her usual routine.

She found a small, folded piece of paper in Ethan's bedside table drawer. His handwriting was messy, filled with cross-outs and scribbles. "Build a treehouse." "Learn to play the drums." Maya felt a wave of… surprise. She had assumed their lives were firmly established. She felt a sudden urge to rebel against the familiar. She almost felt… frantic.

She found herself rummaging through the kitchen cabinets, searching for something, anything, to distract her. She felt a desperate desire to break free from the stagnation she was feeling.

Emotion: restless

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.51 Negative
PC2 (Disposition): -0.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.485
’0.363
S0.333
tìm0.316
destination0.272
Suppressed:
B-0.421
заслу-0.297
টুকু-0.211
arada-0.204
background-0.202