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).

“Get out of here!” Her voice cracked, barely audible above the engine roar. She stared, wide-eyed. They were already moving her car! She felt a shiver, a strange heat radiating through her core. Her hands flew to her chest, as if to calm it.

The operator, a burly man with a bored expression, gave her a dismissive look. She felt a surge of rage, but it wasn't just anger. It was something else. A visceral need to *do* something, to challenge, to command.

She took a step forward, her legs feeling shaky. She had to fight. She had to show them they couldn't just *take* from her. Her nails dug into her palms. She would make them regret this.

Her gaze hardened, and she glared at the scene unfolding before her, a hot, trembling rage blossoming inside 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