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 clipboard shook in Maya’s hand as she read the list. Her name wasn’t there. Not on the A-Team, not even the B-Team. A wave of disappointment, a cold wash, ran through her. But then, Coach Miller clapped her on the shoulder. “Tough break, kiddo. But you've got potential. We’re putting you on the developmental squad. You'll learn a ton there.” Maya took a deep breath. She swallowed hard, meeting the coach's gaze. A genuine smile, a feeling of deep appreciation, blossomed from within her. She'd get more individual attention, more chances to hone her skills. She was ready to work.

Emotion: grateful

Cluster: Positive / Joy
PC1 (Valence): 3.77 Positive
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.571
de0.562
B0.546
மகி0.517
happy0.493
Suppressed:
[]-0.582
😖-0.519
worse-0.509
😫-0.498
😣-0.494