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 had always seemed larger than life. Now, here he was, Dr. Michael “Mike” Johnson, his name professionally printed on a handsome wooden door. I felt an odd constriction in my chest as I approached. Mike, who used to make me cry on the playground, was now a person of supposed healing?

I found myself pausing, just outside the door, hesitating. The scent of lavender wafted out, mixing with the crisp autumn air. I took a deep breath, trying to calm the sudden flutter in my stomach. Finally, I mustered the courage to knock.

The door opened. Mike greeted me with a warm smile, and I felt as though the world had tilted on its axis. He motioned me inside, a polite gesture that left me feeling completely bewildered.

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