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 watched the new recruit, fresh from college, stumble through the data entry process. His shoulders felt heavy, the weight of the tasks still remaining. He took a sip of lukewarm coffee. The coffee tasted bitter. The air in the office was stale, thick with unspoken thoughts.

"Do you understand?" he finally asked. There was a pause. The recruit nodded hesitantly. He continued his work, his fingers moving with a slow rhythm. He had been through this cycle many times before.

He felt an odd disconnect, like he was watching a play. The recruit seemed to be the main character, and he was a mere observer. He did not feel anything for the proceedings. The training went on, with the new recruit's eagerness and his own detached responses.

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