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 was in the basement, searching for holiday decorations when he found the boxes. “Ben - School Days,” each one was labeled in his mother’s familiar handwriting. He hadn’t known. He was floored.

He opened one and found a world of memories. A report card, his first ever, with a note from his teacher. A drawing of a superhero, his imagination as vibrant as the colors on the page. Each piece was a thread woven into the tapestry of his life.

He felt a deep sense of respect, a feeling of… wonder, as he realized the depth of his mother’s love. He picked up a drawing he made of a car at age six. He remembered the joy. The care, the time, the devotion… It was overwhelming.

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