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).

"Can't you ever be ready on time?" Sarah muttered under her breath, pacing the narrow aisle of the used bookstore. Liam was picking out a book, she’d been here for ages, and they needed to leave.

She was the one who had spotted this charming little shop, but her eagerness to find a book to take on their trip had faded. A slim volume, “Selected Poems of Frost,” caught her eye. She reached for it, her fingers brushing against something tucked inside.

A letter. The paper crinkled at the edges, and the ink was faded. The words whispered of a forgotten love, of promises made and broken. Sarah, as she unfolded the letter, felt a surprising pang of regret. She would have preferred to be anywhere else.

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