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 clock in the living room ticked with maddening precision. Leo sat on the floral sofa, the fabric scratching against his jeans, a sensation he found acutely irritating. He stared at the flickering flames in the fireplace, a spectacle he usually found mesmerizing, but tonight it held no allure.

His leg bounced, a frantic rhythm against the worn rug. He'd tried reading, but the words blurred before his eyes. The silence, normally a refuge, was now a tormentor, filled with the echo of his own unproductive thoughts.

"Dinner's ready, honey!" his mother called from the kitchen. He winced. The scent of pot roast, a childhood favorite, assaulted his senses, adding to his unease. He felt trapped, a fly buzzing in a glass jar.

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