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 sheer scale of the situation, the weight of the request, was almost too much. I found myself staring at the proposed tree removal contract as if it were a priceless artifact. Mrs. Gable's eyes were fixed on me, waiting. But all I could focus on was the tree itself.

A shiver traced its path down my spine, though the day was warm. I considered the oak's history, its silent witness to all the neighborhood dramas. It was a tangible link to something bigger than myself. My throat constricted.

The air around me seemed to crackle with an unseen energy. I realized the tree was more than just a tree. It was a symbol, an anchor to the earth, a monument to the relentless passage of time. I muttered about considering the proposition, and then immediately went back inside.

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