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 first crack of the jackhammer pierced the morning stillness, but Amelia just grinned. She’d been waiting for this. New neighbours, a fresh start for the whole street. She poured herself a cup of coffee and strolled onto her porch, the rising sun warming her face.

Her own garden needed some serious attention, a project she’d been putting off. Now, with the sound of progress next door, she felt a sudden surge of motivation. The air practically hummed with possibility.

She pictured herself, trowel in hand, transforming her neglected flowerbeds into a riot of color. She grabbed her gardening gloves and a wide-brimmed hat, the scent of damp earth already filling her imagination. Today was the day.

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