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 humid air of the jazz club pressed against Leo’s skin. He’d come to blow off some steam, but the opening act, a sultry-voiced woman named Selena, was tearing down the house. She was taking liberties with his song, “Midnight Bloom,” bending the melody, embellishing the bridge, but somehow…making it better. A heat bloomed in his chest. His fingers tapped a rapid rhythm against his thigh, mirroring the drummer’s relentless pulse. He leaned forward, eyes glued to Selena as she hit a high note, and swallowed hard.

The saxophone solo was pure fire. He felt a flush climb his neck, tracing the edge of his ears. The way she moved, the way she inhabited the song, the way she was making it *hers*... It made him want to stand up and shout, to throw something, to just *feel* something. His palms were slick.

He saw her wink at him during the final instrumental flourish, and his heart hammered against his ribs.

Emotion: aroused

Cluster: Alertness
PC1 (Valence): -0.45 Negative
PC2 (Disposition): -1.13

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.386
S0.383
P0.379
own0.376
悸0.344
Suppressed:
a-0.877
l-0.501
de-0.474
que-0.438
been-0.384