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’d arrived at work early, as usual, but today felt different. David smoothed the crease in his perfectly tailored suit, a silent acknowledgment of the importance of the meeting. The air in the office crackled with an energy he hadn't noticed before, and he enjoyed the feeling.

The interview was a breeze. He'd rehearsed his answers, knowing he was the best candidate. As he sat across from the panel, his confidence radiated. He even made a joke, and it landed perfectly.

Walking out of the conference room, David felt a lightness in his step. The news was inevitable, he knew. He already imagined the corner office, the increased responsibility. He almost wanted to skip down the hallway.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.514
la0.457
😎0.400
happy0.394
πŸ‘0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
πŸ˜–-0.453