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 flickering candlelight cast dancing shadows on the walls of the old library, making the room seem even colder than it was. He was exhausted. A sleepless night and now this. Michael wanted to be anywhere else. This stupid memory.

"Are you sure the book was red?" asked David, his voice a low murmur.

Michael ran a hand through his hair, the gesture almost violent. He’d gone over this a hundred times. "Yes! Absolutely red. Not blue, not green, red!" He felt a surge of frustration.

David paused, studying the worn leather cover of the book in his hands. "It just seems… darker than I remember."

Michael took a deep breath, trying to tamp down the rising tide of exasperation.

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