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).

Liam drummed his fingers on the cardboard box, the hollow thud echoing in the quiet study. He shifted his weight, legs aching from standing. He had a million other things he could be doing, things he *wanted* to be doing. He’d promised to call a friend, catch up on some shows. Now, here he was, sifting through his mother’s old homework.

He flipped through a math quiz, the answers scrawled in a frantic hand. Then a book report on *The Hobbit*, heavily underlined and annotated. He felt his jaw clench. This was going slower than molasses in January. He glanced at the clock, a knot forming in his stomach. How much longer?

Emotion: impatient

Cluster: Anger / Hostility
PC1 (Valence): -0.33 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.527
impatiently0.434
impatient0.413
S0.396
impatience0.351
Suppressed:
な-0.298
s-0.298
newfound-0.272
께서-0.265
заслу-0.264