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 relentless Florida sun beat down on Sarah’s back as she rummaged through the clutter. Then, she saw him: Mr. Snuggles, her beloved childhood teddy bear, looking surprisingly well-preserved considering his age. Her breath hitched.

Her hand flew to her mouth, and a giggle escaped her lips. The woman selling the items beamed at her, instantly understanding the moment.

Sarah couldn't stop grinning as she cradled Mr. Snuggles against her chest, a sweet, silly sensation coursing through her. She felt like a child again, the world brimming with color and adventure. She knew immediately he was going to join her on the road trip she had planned.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
🤩0.495
Suppressed:
S-0.896
😞-0.430
ness-0.410
それでも-0.387
L-0.379