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).

He bounced his leg, the wood floor of his mother’s apartment creaking in protest. Thomas ran a hand through his already messy hair, leaving it standing on end. He was supposed to be honoring her memory, not wasting his Saturday. He sighed, blowing a stray strand of hair from his face. The estate lawyer had said this was important. He found a small, yellowed notebook tucked inside her favorite cookbook.

The first item on the list: “See the Northern Lights.” He rolled his eyes. This was just like her, always chasing some grand, impossible dream. He felt a prickly heat rise in his cheeks. He just wanted to get this over with, to move on.

“Take a pottery class,” read the next line. Thomas scoffed audibly. He felt a need to break something, to shatter the suffocating quiet. He longed for action, for something to *happen*. He slammed the book closed, the sound echoing in the stillness.

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