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 email notification pinged, and Chloe practically lunged for her laptop. "An example essay..." The words swam before her eyes. The familiar essay, her essay, was now a public spectacle. She scanned it, her heart thudding a rapid rhythm against her ribs.

She was due to graduate in three months, with no job prospects. The feeling in her chest was like a stretched rubber band, ready to snap. She had sent out dozens of applications and heard back from nothing. Was the essay *too* honest? *Too* vulnerable?

She bit at her thumbnail, the taste metallic. She felt a tremor in her hands. The silence from the potential employers was maddening. She needed to know, she needed to be moving. She needed *something*.

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