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 house, nestled amongst the towering pines, seemed to exhale a sigh as Elias approached. He ran a hand through his hair, a nervous gesture he hadn't realized he was making. This was his and his sister, Clara's, responsibility now. He remembered visiting here as a boy, the scent of his grandmother's lavender soap still potent in his memory.

Clara, practical as always, was already fiddling with the lock. He watched her, a strange mix of emotions swirling inside him. He stood back, feeling strangely out of sync with his body.

He watched her push the door open. He took a deep breath, trying to calm the sudden thumping in his chest.

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