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 crisp autumn air bit at Maria's cheeks as she walked home, the setting sun painting the sky in fiery hues. Her teammates' faces, usually bright with camaraderie, were now a blur, their words of support echoing in her ears like a distant symphony. Coach Thompson's decision was a surprise, an unexpected blow. She had no clue what to do.

She stopped at the park, the swing set swaying gently in the breeze. She remembered swinging there as a kid, all joy and freedom. Now, the world was a different place.

She felt a hollowness inside, a vast empty space where her passion had once resided. She sat on the cold metal and began to swing, back and forth, the motion a mindless rhythm that she hoped might calm her racing thoughts. Each pass across the sky was a lost moment, a missed opportunity.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219