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 hammering of the doorbell had stopped. Finally. Brenda cracked open the front door, the sun hitting her directly in the face. Mr. Henderson from next door stood there, a sheepish look on his face. “Brenda, quick word? About that old oak…” She sighed internally. This was the third time he'd come over this week.

He gestured towards the tree, its leaves already starting to turn. "Bit of a hazard, you see. Roots, and all that." Brenda crossed her arms, the skin prickling at the back of her neck.

"Sure, Mr. Henderson." She wanted this over with. Now. "What's the plan?" He began to ramble about permits and quotes, each word stretching the moment. Brenda tapped her foot, the rhythm mirroring the frantic beat in her chest.

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