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 sun blazed, warming Amelia’s face as she arranged the balloons, their bright colours vibrant against the clear blue sky. It was her birthday, and she'd decided on a beach bonfire. Perfect.

Across town, Daniel was hosting a gala, a grand, expensive event. She shrugged, dismissing it from her mind. This was her vision. The crackling fire, the sand between her toes, the friendly faces.

She glanced at the waves, a slow smile gracing her lips. She could almost hear the music, the chatter, the joy. Her stomach fluttered with a quiet energy, a bubbling excitement that made her feel light as a feather.

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