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 envelope lay on the kitchen table, stark white against the dark wood. Sarah stared at it, her hands hovering above it. She had been on edge all morning, the feeling bubbling in her chest. She grabbed it.

She’d spent the last month researching adoption, connecting with support groups. Each story, each shared experience, only intensified her desire for her own truth.

Taking a deep breath, she ripped open the envelope. The paper fluttered open. She skimmed the introductory paragraphs, each word a further delay. She wanted to skip to the end, to the names, to the faces, to the *answers*. But she forced herself to read, though her eyes jumped across the words, desperate for the reveal.

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