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 realtor’s words hung in the air, thick and heavy. “It was… a rather notorious situation. Back in ‘87.” Sarah stared at the pristine white walls of her recently renovated kitchen, suddenly seeing the space differently. A chill snaked up her spine despite the warmth radiating from the oven. She ran a hand over the smooth, granite countertop, her fingers tracing the clean line. This was where *it* had happened.

She felt a strange disconnect. This perfectly normal kitchen, the heart of her home, had once been the backdrop for something terrible. The very air seemed to vibrate with a history she couldn't comprehend. She needed air, suddenly, and stepped out onto the back patio, the late afternoon sun offering little comfort.

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