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 paper crackled under her fingers, the words burning into her mind. “Condo Conversion.” The world around her sharpened, colors became more intense, sounds more distinct. She felt a lightness in her chest, a feeling she hadn't experienced in years.

She turned on some music, the beat pulsing through her veins. She started dancing, moving with a frenetic energy she couldn't contain. She moved furniture around, making a clear dance floor in the living room.

She danced until her muscles ached, until sweat poured down her forehead. The exertion was exhilarating, a release. Her laughter filled the apartment, a sound of pure, unadulterated joy. She was alive, fully engaged, embracing the unknown with open arms.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354