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 office doors seemed to swing open wider than usual, as Mark sauntered into work. He felt like he could take on the world; the project was progressing well, and the recent promotion was giving him wings. He grinned at his coworkers, a warmth emanating from within.

The announcement crackled through the intercom. Mark's jaw dropped, a wave of cold washing over him. The world seemed to shrink around him.

The energy he'd felt moments before—that sense of invincibility—collapsed. The future, previously a wide-open vista, now narrowed into a dark, uncertain path. He felt a deep, sickening lurch in his stomach.

Emotion: vibrant

Cluster: Positive / Joy
PC1 (Valence): 2.83 Positive
PC2 (Disposition): -1.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
!0.459
!".0.436
de0.434
!).0.409
Suppressed:
S-0.890
L-0.478
P-0.407
H-0.365
😞-0.306