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 antique shop was stifling, the air thick with dust and the scent of aged wood. Elias ran a hand over a tarnished silver mirror, his fingers drumming a nervous rhythm against the cool metal. He’d already browsed every aisle twice, each object failing to hold his attention for more than a fleeting moment. His leg jiggled incessantly, a nervous tick he couldn't seem to control. A sudden chime from the front door sliced through the quiet, and a woman with fiery red hair entered, her eyes scanning the room with a similar intensity.

She approached him, a small, worn leather-bound book clutched in her hand. "Do you know anything about the markings on this?" she asked, her voice carrying a tremor.

Elias squinted at the symbols, a familiar heat blooming in his chest. "Yes," he blurted out. "Those are…they're characteristic."

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