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 elevator doors opened onto the fifth floor, and Amelia practically skipped out. A new team, a new challenge – the marketing department! Her chest felt light, like she could float away. The previous weeks spent in accounting had felt… stifling. Now, the air buzzed with a different energy. She bounced on the balls of her feet as she walked toward the open-plan office, taking in the colorful posters and the scent of freshly brewed coffee.

A woman with fiery red hair and a dazzling smile strode toward her. "Amelia, right? Welcome! I'm Sarah, your new team lead. We're so thrilled to have you." Amelia grinned back, feeling a warmth spread through her.

“The feeling is mutual,” she replied, her voice brimming with excitement. She couldn't wait to see what lay ahead. This felt right.

Emotion: hopeful

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.715
la0.549
B0.468
🤩0.452
enthusi0.433
Suppressed:
S-0.603
不-0.401
😞-0.399
worse-0.394
C-0.386