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 crisp autumn air nipped at Maya’s cheeks as she practically skipped across the quad, a wide grin plastered on her face. Her hands, shoved deep in her pockets, were already tingling with anticipation for the after-school art club meeting. She'd poured her heart into that final project, a sprawling mural depicting a fantastical underwater world. She felt a lightness, a buoyant feeling, like she could float away.

She found the grade posted outside Professor Davies’ office. Her heart did a little flip, a flutter of excitement. She approached the board, already picturing that A+ she was sure she had earned. Her eyes scanned the list, finally landing on her student ID number. The grade next to it was a jarring, unexpected C-.

A wave of confusion washed over her, but it quickly receded. Well, that's unexpected. Maybe the professor made a mistake. A small 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