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).

"Oh. My. God." Amelia whispered, her voice barely audible. The email gleamed on her phone screen, the words "Student Spotlight" sparking a wildfire of feeling. She slammed her phone shut, then instantly opened it again, her thumb hovering over the link. A gasp escaped her lips as she scrolled through the website. There it was: her essay, her name, her words.

A dizzying rush of energy surged through her. She felt a lightness, an almost weightless sensation, as if she could float right off her chair. She grabbed her sketchbook, flipping to a blank page, her fingers already itching to translate this feeling into lines and shapes. She needed to create, to channel this… this… well, whatever it was, into something tangible.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🤩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
😔-0.300