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 screen illuminated with his name. “Brian Evans wants to be your friend.” It had been so long. The memories, however, were still vivid. He had been a source of both fear and… something else, a strange thrill. A tingling sensation spread across her skin.

She reached for the mouse, her hand trembling slightly. She needed to breathe, to slow her racing heart. She clicked on his profile, a photo of a man she barely recognized stared back.

She felt a tightening in her chest, a sort of excited dread. She wanted this. She needed this. She had to *know*. She clicked "Accept" without hesitation, the world warping around her.

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