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 attic air hung thick with dust motes dancing in the lone sunbeam. Clara hummed a tuneless melody, carefully lifting a cardboard box labeled “Grandma Elsie - Memories.” She felt a warmth in her chest, a lightness that made her eager to uncover the secrets within.

A faded sepia photograph lay nestled amongst yellowed letters. The woman in the picture, undeniably Elsie, was perched on a motorcycle, wind whipping through her hair, a mischievous glint in her eyes. The Elsie Clara knew, the one who baked apple pies and whispered about angels, never mentioned owning a motorcycle.

Clara traced the image with a fingertip, a smile blooming on her face. This was a different Elsie, vibrant and adventurous. "Wow," she breathed, her voice filled with wonder. She couldn’t wait to learn more.

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