diff --git a/README.md b/README.md
index 678351a8..7c4dea82 100644
--- a/README.md
+++ b/README.md
@@ -719,7 +719,7 @@ npm install @xenova/transformers
 | Provider | Model | Cost | Notes |
 |---|---|---|---|
 | **Local (recommended)** | `all-MiniLM-L6-v2` | Free | Offline, +8pp recall over BM25-only |
-| Gemini | `text-embedding-004` | Free tier | 1500 RPM |
+| Gemini | `gemini-embedding-001` | Free tier | 100+ languages, 768/1536/3072 dims (MRL), 2048-token input. Replaces `text-embedding-004` ([deprecated, shutdown Jan 14, 2026](https://ai.google.dev/gemini-api/docs/deprecations)) |
 | OpenAI | `text-embedding-3-small` | $0.02/1M | Highest quality |
 | Voyage AI | `voyage-code-3` | Paid | Optimized for code |
 | Cohere | `embed-english-v3.0` | Free trial | General purpose |
diff --git a/src/config.ts b/src/config.ts
index 2898552d..a4b676cf 100644
--- a/src/config.ts
+++ b/src/config.ts
@@ -76,7 +76,7 @@ function detectProvider(env: Record<string, string>): ProviderConfig {
     }
     return {
       provider: "gemini",
-      model: env["GEMINI_MODEL"] || "gemini-2.0-flash",
+      model: env["GEMINI_MODEL"] || "gemini-2.5-flash",
       maxTokens,
     };
   }
diff --git a/src/providers/embedding/gemini.ts b/src/providers/embedding/gemini.ts
index 74dca6f5..6cfb2764 100644
--- a/src/providers/embedding/gemini.ts
+++ b/src/providers/embedding/gemini.ts
@@ -2,7 +2,8 @@ import type { EmbeddingProvider } from "../../types.js";
 import { getEnvVar } from "../../config.js";
 
 const BATCH_LIMIT = 100;
-const API_BASE = "https://generativelanguage.googleapis.com/v1beta/models/text-embedding-004:batchEmbedContent";
+const MODEL = "models/gemini-embedding-001";
+const API_BASE = `https://generativelanguage.googleapis.com/v1beta/${MODEL}:batchEmbedContents`;
 
 export class GeminiEmbeddingProvider implements EmbeddingProvider {
   readonly name = "gemini";
@@ -29,8 +30,9 @@ export class GeminiEmbeddingProvider implements EmbeddingProvider {
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify({
           requests: chunk.map((t) => ({
-            model: "models/text-embedding-004",
+            model: MODEL,
             content: { parts: [{ text: t }] },
+            outputDimensionality: this.dimensions,
           })),
         }),
       });
@@ -45,10 +47,31 @@ export class GeminiEmbeddingProvider implements EmbeddingProvider {
       };
 
       for (const emb of data.embeddings) {
-        results.push(new Float32Array(emb.values));
+        results.push(l2Normalize(new Float32Array(emb.values)));
       }
     }
 
     return results;
   }
 }
+
+let zeroNormWarned = false;
+
+function l2Normalize(vec: Float32Array): Float32Array {
+  let sum = 0;
+  for (let i = 0; i < vec.length; i++) sum += vec[i]! * vec[i]!;
+  const norm = Math.sqrt(sum);
+  if (norm === 0) {
+    if (!zeroNormWarned) {
+      zeroNormWarned = true;
+      process.stderr.write(
+        `[agentmemory] warn: gemini-embedding-001 returned a zero-norm ` +
+          `embedding (length=${vec.length}); leaving it un-normalized. ` +
+          `Subsequent zero-norm vectors will not be reported.\n`,
+      );
+    }
+    return vec;
+  }
+  for (let i = 0; i < vec.length; i++) vec[i] = vec[i]! / norm;
+  return vec;
+}