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 world felt… brighter today, Ms. Rodriguez thought, as she walked into her classroom. She paused, taking a deep breath of the stale air, which somehow still smelled sweet with the promise of learning. Her heart gave a little skip.

A small, brightly-wrapped gift sat on her desk, a cheerful splash of color against the usual drabness. It was tied with a ribbon that perfectly matched her favorite scarf. She couldn’t remember the last time she’d been this intrigued.

Inside was a collection of vintage postcards, each depicting a different city in Italy. A handwritten note read, "Thinking of you. - Maria." Maria, who had always dreamed of traveling the world. A gentle chuckle escaped her lips.

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