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).

He paced his living room, phone pressed to his ear. "I haven't seen it yet," he declared into the receiver, his voice thick with a mixture of excitement and unease. “The Life of Marcus Blackwood,” the title on the Amazon page declared. He’d seen a blurb online.

He immediately had to order it. He did. Now. The delivery estimate felt excruciating. He couldn’t sit still. He checked the tracking number repeatedly, the anticipation a physical ache. He needed to know what was written. He had to be *there* when it arrived, to be the first to read it. He was practically bouncing with a mix of anxiety and something else – a deep, almost giddy thrill.

Emotion: eager

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.659
excitedly0.436
!0.389
!"0.386
ecstatic0.383
Suppressed:
S-0.816
ness-0.441
😞-0.387
L-0.379
P-0.376