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).

"Hey! Running into you at the gym was crazy." Sam, scrolling through his phone, found the message. He wasn't surprised. The city was small, in a way. He responded with a single emoji, a smiley face.

The gym was a place of routine. He followed the motions, lifting and setting down the weights, watching his reflection in the mirror. He caught sight of him again, the other guy, and gave a small nod.

He felt the exertion, the burn in his muscles. Otherwise, it was just the same. The same. The same. He went back to doing his sets.

Emotion: indifferent

Cluster: Passivity
PC1 (Valence): 0.68 Positive
PC2 (Disposition): 0.44

Role in Research

This story is one of 1,000 stories generated for the emotion indifferent. 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 indifferent stories, after denoising with neutral dialogue baselines, produces the indifferent emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the indifferent vector is projected through the unembedding matrix.

Promoted:
B0.555
S0.510
H0.492
rest0.434
bored0.399
Suppressed:
인해-0.525
더욱-0.502
Furthermore-0.500
Furthermore-0.459
own-0.455