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 stared at his son, Alex, his jaw slackening. His intricate origami creations had always been a solitary pursuit, a meditative practice. Now, Alex, age six, had taken up the craft.

He watched Alex work with a piece of paper, mimicking his every move, his little fingers meticulously folding and creasing. The result, a perfect crane, sat on the table.

He felt something twist inside him. It was a mirroring of his own soul. He remembers that feeling from when he was a boy himself! This was more than just a hobby; it was a connection, a bond. He felt a profound sense of… something.

"Can you teach me how to make a dragon next, Dad?" Alex asked, his voice full of hope.

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