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 flickering candlelight cast dancing shadows across the dining room walls as Emily watched her fiancé, Ben, return from his latest clandestine phone call. The last few weeks had been a nightmare, the constant anxiety gnawing at her insides. Every whispered word, every secretive glance, had felt like a stab to her heart.

Ben returned, his face a mixture of emotions she couldn't quite decipher, but his eyes were filled with an unusual brightness. He offered her a small, almost sheepish, smile.

"I called my dad," he said, his voice quiet. "To get the details sorted."

She felt a wave of warmth spread through her, thawing the icy grip that had held her in its grasp. He hadn't been cheating; he'd been planning. Her shoulders slumped in a wave of relaxation, and she felt the tension leak away from her body.

Emotion: relieved

Cluster: Positive / Joy
PC1 (Valence): 2.22 Positive
PC2 (Disposition): -0.97

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.638
finally0.606
finalmente0.597
relieved0.561
enfin0.546
Suppressed:
l-0.443
:(-0.439
😣-0.429
S-0.388
😖-0.385