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 florist’s truck had barely vanished from the driveway when she was already rummaging through the flowers. A mixed arrangement of wildflowers, they were charming enough, but the lack of a card was infuriating. She flipped each bloom over, examined the stems, and shook them, as if a secret might fall out.

She stomped back inside, tossing her keys onto the table with unnecessary force. The house felt too quiet. She needed answers. She considered calling her best friend, then dismissed the idea. Better to figure this out herself.

She took a deep breath, and walked to the table. She ran her fingers across her lips. Time was ticking. She wanted to know who it was. The thought of waiting was too much.

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