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).

"My word," Martha breathed, clutching her pearls. The roar of the cement mixer was deafening, but she didn’t care. She was completely captivated. Mr. Davies was pouring a new foundation. She had known he planned some updates, but she hadn’t expected anything of this scale.

She watched, transfixed, as the wet concrete flowed, a viscous river reshaping the earth. The energy on display was almost tangible, a current running through the quiet neighborhood.

She felt a rush of adrenaline. She knew nothing about construction, but she found herself picturing it. She closed her eyes for a moment, and saw it fully. She even felt a desire to pick up a shovel and help.

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