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).

"Did you see the notice?" Brenda asked, her voice laced with incredulity. She held up a crumpled flyer, her eyes wide. "Mr. Grumbly wants to put up a fence!"

I stared at her, then glanced at the shared boundary line. It was an open space. We’d discussed planting a garden together, just last week. A barrier? A cold wash of sensation flooded me. I didn't get it. I felt my stomach flip.

"I can't believe it," she continued, shaking her head. "After all this time."

My thoughts were a jumble, processing her statement. I hadn't seen this coming.

Emotion: surprised

Cluster: Surprise / Confusion
PC1 (Valence): -0.58 Negative
PC2 (Disposition): -0.18

Role in Research

This story is one of 1,000 stories generated for the emotion surprised. 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 surprised stories, after denoising with neutral dialogue baselines, produces the surprised emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the surprised vector is projected through the unembedding matrix.

Promoted:
que0.495
de0.447
la0.431
l0.323
😳0.296
Suppressed:
每天-0.269
cheerfully-0.249
ing-0.238
alleviate-0.224
gladly-0.219