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 stuffy confines of the genetics conference hall felt suffocating. Dr. Ramirez, an expert in the field, was outlining the intricacies of the condition. He was interrupted by a commotion near the back. A young man was attempting to shove his way through the crowd, a frantic look on his face.

The man came to a halt. His eyes widened as they locked with someone else in the crowd. A woman stared back at him with an equally shocked expression. The lecture became irrelevant.

Ramirez paused, his face unreadable. The air in the room seemed to thicken, a current of shared bewilderment and something deeper. The woman’s lips parted in a silent gasp as the man made his way toward her.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238