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).

Sunlight streamed through the window, warming Ms. Eleanor's face as she sat at her desk. It had been a long term, with endless lesson plans and mountains of marking. Now, the summer loomed. A gentle knock on the door startled her. A young man stood there, holding a small, intricately carved wooden box. It was Daniel, a student from five years prior. His eyes, once mischievous, now held a quiet confidence.

"Ms. Eleanor," he began, his voice a low rumble. "I wanted to… I made this. For you. For helping me." He offered the box.

She accepted it, her fingers tracing the smooth, cool wood. A small smile played on her lips as she opened it to find a single, perfect white orchid. Its delicate fragrance filled the room, chasing away the stale air of the classroom. The worries she'd carried melted away, replaced by a lightness she hadn't felt in months.

Emotion: refreshed

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): -1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.998
de0.703
!).0.384
(!)0.381
!".0.379
Suppressed:
S-0.782
C-0.478
L-0.414
😣-0.388
😞-0.376