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 held the dusty trophy in his hands. He felt a jolt. The attic’s dusty air seemed to amplify everything. He stared at the name etched on the silver plate: "James Harrison, State Champion, 1958."

A stack of old photographs lay nearby. He flipped through them, seeing James Harrison at the peak of his youth, on the field, smiling with his teammates. He felt a sudden respect for the man he had never met.

The attic had suddenly been transformed. He imagined James's life, his triumphs, and his sorrows. He felt a strange sort of fellowship with this stranger, a respect for his achievements. He knew he'd never forget his time in the attic.

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