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 silence that descended after the initial panic was broken by the rhythmic tapping of Eleanor’s foot. She bounced her leg, her eyes alight with a barely-contained enthusiasm. She turned to Michael, the other trapped occupant. "Well, this is… interesting," she announced, her voice filled with a lighthearted lilt.

Michael looked as though he wanted to scream. Eleanor, on the other hand, felt a surge of energy course through her veins. This was a chance to escape the monotonous routine of the office, the endless stream of emails and meetings.

She’d been itching for a distraction, something to break the tedium. She reached into her bag, pulling out a sketchpad and a pen. Her fingers itched to begin drawing, to capture the details of the stalled elevator, the expressions on their faces.

Emotion: pleased

Cluster: Positive / Joy
PC1 (Valence): 3.62 Positive
PC2 (Disposition): -0.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.728
la0.496
happy0.462
🤩0.433
🥳0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401