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 notice fluttered in Amelia’s hand, the words ‘University Closure’ swimming before her eyes. Instead of dread, a giggle bubbled up. She pictured the drab lecture halls, the echoing library – gone! She tossed the paper onto her cluttered desk, a wide grin plastered across her face. This was it, the chance to finally pursue that pottery course she’d been daydreaming about. Her heart felt light, almost like it was doing a little dance inside her chest.

The thought of no more mandatory Shakespeare readings filled her with a thrilling energy. She practically bounced down the hallway, humming a jaunty tune. She practically skipped over to Sarah, her roommate, and exclaimed, “Guess what? We’re free!”

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
🤩0.515
Suppressed:
S-0.891
😞-0.504
L-0.486
ness-0.478
それでも-0.432